arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.14718cs.LGcs.AIcs.RO
收藏

利用多任务表示学习提高自主车辆策略学习效率

Increasing the Efficiency of Policy Learning for Autonomous Vehicles by Multi-Task Representation Learning

Aalto University(阿尔托大学)

Eshagh Kargar, Ville Kyrki

摘要:

在动态、多智能体和复杂的城市环境中驾驶是一项艰巨的任务,需要复杂的决策策略。这种策略的学习需要一个可以对整个环境进行编码的状态表示。将车辆环境编码为图像的中级表示已成为流行的选择。尽管如此,它们是非常高维的,限制了它们在数据饥渴方法中的使用,例如强化学习。在这篇文章中,我们提出了一个低维和丰富的潜在表示的环境,利用相关的语义因素的知识。为此,我们训练一个编码器-解码器深度神经网络来预测多个与应用相关的因素,例如其他代理和自我汽车的轨迹。此外,我们提出了一个危险信号的基础上,其他车辆的未来轨迹和规划的路线,这是结合学习的潜在表示作为输入到下游的政策。我们证明,使用多头编码器-解码器神经网络的结果在一个更丰富的表示比一个标准的单头模型。特别是,所提出的表示学习和危险信号有助于强化学习更快地学习,与基线方法相比,具有更高的性能和更少的数据。

英文摘要:

Driving in a dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision-making policy. The learning of such a policy requires a state representation that can encode the entire environment. Mid-level representations that encode a vehicle's environment as images have become a popular choice. Still, they are quite high-dimensional, limiting their use in data-hungry approaches such as reinforcement learning. In this article, we propose to learn a low-dimensional and rich latent representation of the environment by leveraging the knowledge of relevant semantic factors. To do this, we train an encoder-decoder deep neural network to predict multiple application-relevant factors such as the trajectories of other agents and the ego car. Furthermore, we propose a hazard signal based on other vehicles' future trajectories and the planned route which is used in conjunction with the learned latent representation as input to a down-stream policy. We demonstrate that using the multi-head encoder-decoder neural network results in a more informative representation than a standard single-head model. In particular, the proposed representation learning and the hazard signal help reinforcement learning to learn faster, with increased performance and less data than baseline methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑